IntelliRec: Frequently Asked Questions Hybrid Recommendation System for Personalized Placement Preparation

DOI

10.2991/978-94-6463-866-0_27How to use a DOI?

Keywords

FAQ Recommendation; CTGAN; Hybrid BM25-XGBoost Model

Abstract

IntelliRec is an intelligent FAQ recommendation system designed to enhance placement preparation by delivering company-specific frequently asked questions (FAQs). Traditional question banks are often static and fail to adapt to evolving recruitment patterns, leading to redundant and inefficient study approaches. IntelliRec addresses this by implementing a hybrid ranking model that combines BM25 for initial retrieval and Learning-to-Rank (LTR) using XGBoost for refined ranking, ensuring the most relevant and frequently asked questions are prioritized. This helps candidates focus on high-impact questions and optimize their preparation strategies. To tackle the challenge of limited data, synthetic records were generated using Conditional Tabular GAN (CTGAN), enriching the dataset and improving model robustness. A chi-square test on the synthetic data yielded a p-value of 0.98, indicating no significant imbalance compared to the original dataset. IntelliRec integrates natural language processing techniques and machine learning to deliver precise, company-aligned recommendations. The system achieved strong performance metrics, including a precision@k of 92%, recall@k of 93%, F1-Score of 93%, and an NDCG of 1.0, demonstrating its effectiveness and scalability. By bridging the gap between static question banks and dynamic hiring practices, IntelliRec empowers candidates with strategic, targeted preparation, making it a valuable tool for navigating modern recruitment processes.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - K. Nivetha
AU  - S. Karthik
AU  - V. Yogieswaran
AU  - M. Indumathy
PY  - 2025
DA  - 2025/10/31
TI  - IntelliRec: Frequently Asked Questions Hybrid Recommendation System for Personalized Placement Preparation
BT  - Proceedings of the International Conference on Intelligent Systems and Digital Transformation (ICISD 2025)
PB  - Atlantis Press
SP  - 321
EP  - 332
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6463-866-0_27
DO  - 10.2991/978-94-6463-866-0_27
ID  - Nivetha2025
ER  -